Learning-Based Visual Saliency Model for Detecting Diabetic Macular Edema in Retinal Image

Figure 6

Some unnormalized saliency map for DME ROIs detection produced by 4 different models from the EDMERI database. Each example shown by one row. From left to right: original image, GT, Ours, ITTI, SR, and Achanta’s. It is obvious that Ours is more similar to the ground truth than other saliency maps.